IT dude
-
gpt-oss-u
Specialized uncensored quants for new OpenAI 20B MOE - Mixture of Experts Model at 80+ T/S. "HERETIC" method results in a model (quantized Q5_1)
thinking 20b30K Pulls 1 Tag Updated 6 months ago
-
deepseek-coder-v2
This is a brand new Mixture of Export (MoE) model from DeepSeek, specializing in coding instructions. (quantized IQ4_XS)
tools 16b16.6K Pulls 3 Tags Updated 6 months ago
-
magistral-small
Building upon Mistral Small 3.2 (2506), with added reasoning capabilities, undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters.(quantized UD-Q5_K_XL)
vision tools thinking 24b886 Pulls 1 Tag Updated 10 months ago
-
yandex-gpt-5-lite
Instruct version of the large language model YandexGPT 5 Lite with 8B parameters with a context length of 32k tokens. (quantised version of Q5_K_M)
8b561 Pulls 3 Tags Updated 10 months ago
-
gigachat3.1
Light version - GigaChat-3.1-Lightning: it shows the level of GPT-4o in arenas, but at the same time remains compact and fast (quantized Q4_K_M)
tools 10b533 Pulls 1 Tag Updated 3 months ago
-
t-lite-it-2.1
T-lite-it-2.1 is an efficient Russian model built upon the Qwen 3 architecture, featuring significant improvements in instruction following and adds support for tool-calling capabilities (quantized Q4_K_M)
tools thinking 8b505 Pulls 3 Tags Updated 6 months ago
-
t-lite-it-1.0
T-lite-it-1.0 is a model built upon the Qwen 2.5 model family and incorporates both continual pre-training and alignment techniques (quantized Q5_K_M)
tools 7b429 Pulls 3 Tags Updated 10 months ago
-
mistral-small-3.2
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors. (quantized UD-Q5_K_XL)
vision tools 24b249 Pulls 3 Tags Updated 10 months ago
-
qwen3-A3B-2507
Qwen3-Thinking-2507 is the continuation of Qwen3 thinking model, with improved quality and depth of reasoning. Qwen3-Instruct-2507 is the updated version of the previous Qwen3 non-thinking mode. (quantized UD-Q4_K_XL, thinking and instruct versions)
tools thinking 30b244 Pulls 2 Tags Updated 11 months ago
-
qwen3-A3B
This is the continuation of Qwen3 thinking model (MOE), with improved quality and depth of reasoning. (quantized UD-Q4_K_XL, thinking without switching off)
tools thinking 30b228 Pulls 3 Tags Updated 9 months ago
-
gemma3-qat
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. (quantized IQ4_XS)
vision 27b158 Pulls 1 Tag Updated 10 months ago
-
t-pro-it-2.1
T-pro-it-2.1 — is an efficient russian model built upon the Qwen 3 model family with improved instruction following and tool-calling capabilities (quantized Q4_K_M)
tools thinking 32b157 Pulls 1 Tag Updated 6 months ago
-
ruadapt-qwen3
GGUF Ruadapt версии модели Qwen/Qwen3-32B (квантизованная версия Q4_K_M)
tools thinking 32b135 Pulls 1 Tag Updated 11 months ago
-
gemma3
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. (quantized UD-Q4_K_XL)
vision 27b122 Pulls 1 Tag Updated 10 months ago
-
ruadapt-t-lite-beta
Адаптация модели T-lite-it-1.0 на русский язык (квантизованная версия Q4_K_M)
tools 7b122 Pulls 1 Tag Updated 11 months ago
-
t-pro-it-2.0
T-pro-it-2.0 is a model built upon the Qwen 3 model family and incorporates both continual pre-training and alignment techniques. (quantized Q4_K_M)
tools thinking 32b41 Pulls 1 Tag Updated 11 months ago
-
t-pro-it-1.0
T-pro-it-1.0 is a model built upon the Qwen 2.5 model family and incorporates both continual pre-training and alignment techniques. (quantized Q4_K_M)
tools 32b32 Pulls 1 Tag Updated 11 months ago